"Traditional Welsh Dish Cawl" matching MCP servers:

Turns a YouTube link into a readable, timestamped Markdown transcript by preferring existing subtitles and falling back to local Whisper transcription, with optional Traditional-to-Simplified Chinese conversion and Obsidian-friendly output.

MCP server that enables AI agents to place real Telegram voice calls and speak a message aloud via TTS, with configurable repeats and call handling.

Provides on-device Chinese speech recognition with traditional Chinese (Taiwan) output via MCP server, HTTP API, and CLI, ensuring privacy by processing audio locally without uploading to cloud services.

MCP server for recognizing and generating images, videos, and audio via DashScope, with support for large video uploads and local output previews.

Enables converting video and audio files into transcripts and Traditional Chinese subtitles using Groq Whisper with a pluggable translation backend, including an English-to-Chinese pipeline and a Chinese-to-Taiwanese-Mandarin proofreading pipeline. Transcriptions run as background jobs whose progress, output subtitle paths, and setup status can be queried through the conversation.

Enables natural language-driven speech synthesis using Fish Audio's Text-to-Speech API, supporting multiple voices, streaming, and flexible configuration.

Bi-directional communication for Claude Code via Voice Calls, SMS, and WhatsApp, allowing users to call Claude, receive callbacks, and interact through multiple channels.

A Model Context Protocol server that enables AI assistants like Claude to initiate and manage real-time voice calls using Twilio and OpenAI's voice models.

Enables MCP clients to place, monitor, and hang up phone calls through authenticated tools, retrieve transcripts, and exchange correlated task results with a waiting host. It supports simulated or live calling with persisted call lifecycle records, duration limits, and idempotent requests.

Enables AI agents to ring or text a user's actual iPhone, read a question or update aloud, and return the spoken answer back to the agent as text. Calls and messages land in a single titled thread per agent, with tools for polling results, waiting for replies, and labeling conversations.

Enables an AI agent to place outbound phone calls through the user's own Twilio account, delivering a spoken message or asking a single question and returning the recipient's transcribed reply to the agent. It exposes just two tools—one-way notifications and one-question calls to a fixed, preconfigured number with built-in rate limits and guardrails.

Self-host a realtime voice-call companion for coding agents. Exposes an MCP endpoint that agents can poll as an alternate input stream.

An MCP (Model Context Protocol) server that provides seamless integration between Fish Audio's Text-to-Speech API and LLMs like Claude, enabling natural language-driven speech synthesis.